Automated classification of audio data and retrieval based on audio classes

The explosive increases in the amounts of audio (and multimedia) data being generated, processed, and used in several computer applications have necessitated the development of audio (and multimedia) database systems. The classiication of audio data into diierent categories is an important task which facilitates eecient indexing and accurate searching. The large number of data items, coupled with the subjective and inexact nature of audio data, make the manual classiication a daunting task and automated classiication schemes highly desirable. This paper presents a scheme for automated classiication of audio data with minimal manual interaction, and a scheme for speeding up the retrieval of relevant audio data using predetermined audio classes. The results of classiication and retrieval using the proposed algorithm are presented.